Multimodal Adaptive Fusion of Face and Gait Features using Keyless attention based Deep Neural Networks for Human Identification

TL;DR

This paper introduces an adaptive deep learning fusion method that combines face and gait biometrics for improved human identification in surveillance, effectively handling environmental variations.

Contribution

It proposes a novel keyless attention-based neural network for dynamic multi-biometric fusion, addressing limitations of classical methods under changing conditions.

Findings

Outperforms state-of-the-art models in biometric fusion tasks.

Effectively handles variations in viewpoint and distance.

Demonstrates robustness in real-world surveillance scenarios.

Abstract

Biometrics plays a significant role in vision-based surveillance applications. Soft biometrics such as gait is widely used with face in surveillance tasks like person recognition and re-identification. Nevertheless, in practical scenarios, classical fusion techniques respond poorly to changes in individual users and in the external environment. To this end, we propose a novel adaptive multi-biometric fusion strategy for the dynamic incorporation of gait and face biometric cues by leveraging keyless attention deep neural networks. Various external factors such as viewpoint and distance to the camera, are investigated in this study. Extensive experiments have shown superior performanceof the proposed model compared with the state-of-the-art model.